The Enigmatic Coastal Taipan: Australia’s Deadly Serpent 🐍

Motivation

By exploring the current data and performing a detailed analysis, researchers and enthusiasts can gain insights into the behavior, distribution, and occurrence patterns of the Coastal Taipans in Australia, which can be useful for a range of ecological, environmental, and conservation studies.

1 Introduction

Australia, with its beautiful landscapes and unique wildlife, is a popular destination for tourists from around the world. Among the fascinating creatures found in this region, the Coastal Taipan (Oxyuranus Scutellatus Scutellatus) takes the spotlight. These snakes are native to both Australia and Papua New Guinea and are known for their extremely venomous bites, making them some of the deadliest snakes in the world. According to Markwell and Cushing (2016), what sets the taipan apart, however, is its reputation as having the most toxic venom of any snake in the world !

Figure 1: The coastal taipan (Oxyuranus scutellatus)

But there’s more to these snakes than their dangerous reputation. The Coastal Taipan and the Inland Taipan are the most well-known species in their group, and they primarily inhabit the northern regions of Australia, blending seamlessly into environments like coastal areas, woodlands, and savannas as can be observed in Figure 1.

In this detailed analysis, we aim to explore the complex connection between tourism in Australia and the encounters people have with the Coastal Taipan. Our journey begins by carefully examining tourism data. We’ll look at trends such as the number of tourists, their reasons for traveling, and their favorite destinations in different parts of Australia. This initial step will help us understand when and where tourists visit.

Moving from tourism to the study of nature, we will investigate data related to sightings of Coastal Taipans. By combining this ecological information with tourism trends, we hope to identify places where tourism and these snakes’ habitats overlap.

In the final part of our analysis, we will delve into the core question: is there a significant link between the presence of these snakes and the level of tourism in a particular area? Our goal is to decide whether tourism has an impact on the sightings of these unique reptiles.

1.1 Data source:

• The data was sourced from the Atlas of Living Australia (ALA) using the galah R package.

• The weather station data to study impact of weather conditions on sightings was sourced from National Climatic Data Centre (NCDC) using rnoaa package in R.

Key assumptions

Based on the literature surveys for the Coastal Taipan, here are our assumptions while moving forward with our analysis:

1. Based on the information from the Australia Museum, the Coastal Taipans are active throughout the year but are observed to be most commonly encountered during late winter to spring (August to December of a calendar year).
2. As can be inferred from its colloquial name, the Coastal Taipans are often observed in the coastal regions of Australia.
3. Based on a study by Billabong Sanctuary, the Coastal Taipans are not endangered and have probably increased in numbers due to the growth in the number of rats (who are the primary prey) in areas close to the human settlements.
4. Coastal Taipans depend primarily on their venom as their defensive mechanism and consider human interactions as an act of aggression. Consequently, the number of sightings across Australia can be considered to be limited to certain regions and in small numbers.
5. The Coastal Taipans, like any other snakes are territorial in nature and do not migrate from their region over the years.
6. We anticipate minimal convergence between snake sightings and tourist destinations, primarily due to the Taipan’s reputation as the most venomous snake globally. It is unlikely that tourists would desire encountering them in their natural habitat; instead, they are more inclined to prefer observing these snakes in controlled environments such as sanctuaries or zoos.
7. We would expect a consistent seasonality to be demonstrated for different visit reasons of the tourism in Queensland.
8. We would expect that ‘holiday’ would be the main purpose of tourist travel to the selected regions in Queensland since it has a lot of tourist destination such as the Great Barrier Reef.

Although we will attempt to accurately analyse the data by obtaining it from reliable repositories, however, it is important to consider the limitations of the dataset while making critical conclusions based on the data in hand. Some of the limitations of the current dataset are delineated as follows:

Limitations of the data

1. Since the data which has been obtained from the Atlast of Living Australia falls under the category of observational data, there could be instances of missing values. These instances will need to be filtered out while analysing the data from the repository.

2. Since the data is obtained from various sources, there could be inconsistencies in reporting the data.

3. While the data collection was done in an extensive and granular manner, there could be a lack of precision of the observations made for the exact latitude and longitude.

4. The dataset obtained from the Atlas of Living Australia only reports for all the Coastal Taipans that have been sighted and recorded. Hence, it does not report the entire population of these reptiles across the various regions of Australia. This may lead to inaccurate conclusions post analysis of the limited data in hand.

5. The dataset here consist of observational data and in particular, occurrences data. Some of the limitations that are prevalent in such datasets are as follows :

   • The data here is obtained from various sources. As a result, there may be non-uniformity in the data provided. Each reporting authority may have their own interpretations of the data they may have provided.
   • The current dataset obtained is a subset of an observational data. These types of data are often plagued with lack of randomisation during the selection of data. This may lead to biases in the dataset such as selection and systematic bias.
   • The data maybe misclassified or filled in non-uniform units by the various sources, leading to lack of accuracy of the overall dataset.

6. The sample size of the wild sightings of Taipan might be too limited to draw any meaning conclusion.

7. Lack of available data in the tourism data set. Some of the major regions with sightings could not be found in the tourism data set (e.g. Cooktown) leading to Daintree being used as a proxy.

8. Assumption of NA’s being treated as wild sightings under “eventID” column would lead to overestimation of wild sightings of Taipan as we cannot distinguish whether the NA’s were due to missing information.

2 Data description

Checking queue
Current queue size: 1 inqueue  running 

2.1 Description of the Variables in the Dataset

The dataset contains data on observations of the Coastal Taipans (Oxyuranus scutellatus scutellatus) in Australia. The dataset has been organized into a tidy format. Below is a detailed description of each salient variable:

Variable Name	Data Type	D escription
decim alLatitude	dbl	The latitude coordinate of the o bservation location.
decima lLongitude	dbl	The longitude coordinate of the o bservation location.
eventDate	date	The date when the o bservation was made.
scie ntificName	chr	The scientific name of the observed species. In this dataset, it’s Oxyuranuss c utellatuss cu tellatus.
taxo nConceptID	chr	A unique URL that provides i nformation about the taxonomic concept for the species.
recordID	chr	A unique identifier for each o bservation record.
dataRe sourceName	chr	The name of the data res our c e /provider.
occurr enceStatus	chr	The status of the ob servation, indicating if the species is present or absent at the location.
ev entRemarks	chr	Special remarks related to the event sighting.
eventTime	datetime	Time of the event sighting.
eventID	chr	A unique ID for each event ob servation.
samp lingEffort	chr	An variable to indicate the sampling technique used.
sampli ngProtocol	chr	A remark for the type of sighting.
Quarter	qtr	A c ombination of year and quarter, re presenting t imestamps.
Region	chr	Text characters denoting region or area names.
Purpose	chr	Text characters related to the purpose or usage.
Trips	dbl	Numerical data re presenting quantities (e.g., trip counts).

3 Initial data analysis

3.1 Data Source

Data Source: The data was sourced from the Atlas of Living Australia (ALA) using the galah R package.

The weather station data to study impact of weather conditions on sightings was sourced from National Climatic Data Centre (NCDC) using rnoaa package in R.

Tourism data was downloaded from Monash A-Z Databases: “Tourism Research Australia online for students”.

3.2 Data Cleaning

Data Cleaning Steps:

Sightings Data

1. The datatype for eventDate has been changed to datetime for accurate temporal analysis.
2. Observations with missing event dates, longitude, or latitude were filtered out.
3. Redundant variables were dropped from the dataset to keep only the salient variables important for the current analysis.

Tourism Data

1. Quarter - Missing values are filled using fill() function. N/A values filled with the last observed non-N/A value. Rows with ‘Total’ were filtered out.
2. Region - Rows with ‘Total’ were filtered out, excluding summary data.
3. Purpose - Created with pivot_longer(), where “Holiday” and “Total” were put into two new columns “Purpose” (reason for travel) and “Trips” (number of trips for that purpose).
4. Trips - Contains the number of trips for each purpose. Data was sourced from “Total” column via pivot_longer().

3.3 Data Quality Check

vis_miss(taipan)

The result of the vis_miss() indicates that about half of the total dataset has missing values. These missing values can be observed majorly in the variables of eventRemarks, eventTime and eventID. In order to improve the quality of the overall data, we will consider either transforming these variables or removing them as a part of feature selection in the following sections.

3.4 Data transformation and feature selection

As we are primarily interested in analysing the wild sightings of the Coastal Taipans across Australia, hence, we will filter out the data obtained from museums and animal sanctuaries. This information has been provided in the event ID column which will be used to filter the required data as shown in the code chunk below. It has been additionally assumed that the occurrences with no mention of the term “museum” have been considered as wild sightings in the context of the current study.

taipan <- taipan %>% mutate(occurrence = if_else(str_detect(taipan$eventID,"museum"),"Museum","Wild"))

Figure ?@fig-dist displays the distribution of Taipan sightings categorized into two types: Museum and Wild. It’s evident from the figure that a portion of the data is sourced from museums, which means these observations don’t represent the natural behavior or occurrence of Taipans in their wild habitats.

For a comprehensive study of the natural behavior or occurrence patterns of Taipans, it’s pertinent to focus solely on the “Wild” type data.

 # Selecting only wild occurrences of Coastal Taipans
taipan_wild <- taipan %>% filter(occurrence =="Wild")

We have observed a total of 240 occurrences across Australia. However, this number has been obtained from the raw data which will need to be cleaned further.

Based on the initial data analysis, we will need to perform the following data cleaning operations:

1. Filter the data with valid sighting date for detailed temporal analysis.
2. Filter the data with valid values of longitude and latitude for detailed spatial analysis.

taipan_wild <- taipan_wild %>% 
  rename(Longitude = decimalLongitude,
         Latitude = decimalLatitude) %>%
  mutate(eventDate = as.Date(eventDate)) %>%
  filter(!is.na(eventDate)) %>%
  filter(!is.na(Longitude)) %>%
  filter(!is.na(Latitude)) %>% 
  select(-c("samplingEffort","samplingProtocol","taxonConceptID","recordID","dataResourceName"))
save(taipan_wild, file=here::here("data/taipan.rda"))

‼️💡 Upon performing the required data cleaning operation, we have a total of 100 wild sightings of Coastal Taipans across Australia. 💡‼️

3.4.1 Combining data of sightings with weather data ⛈️

In order to explore the prevailing weather conditions during the sighting, we will need to merge the datasets from two different sources. Here, we will utilise the weather data reported from the various weather stations in Australia by utilising the RNOAA package which is maintained by the National Oceanic and Atmospheric Administration (NOAA). The following code chunk allows us to obtain the weather conditions, namely precipitation (PRCP), maximum temperature (TMAX) and minimum temperature (TMIN). In order to utilise data from active weather stations, we have filtered those data whose last reported conditions were relayed after the year of 2020.

Once we have obtained the weather data, we need to merge the sighting data with the weather conditions. For this purpose, we can utilise the geographical data (latitude and longitude) to merge the closest weather station data with the location of the Coastal Taipan sighting.

‼️ Since it is difficult to exactly match the latitude and longitude of the sighting to the weather station, hence, we will convert the geographical data into spatial objects and then utilise the nearest feature function to merge the weather conditions of the location of the sighting to the closest weather reporting station. This has been done in the following code chunk. ‼️

# Convert the datasets into spatial objects
taipan_sf <- st_as_sf(taipan_wild, coords = c("Longitude", "Latitude"), crs = 4326)
aus_stations_sf <- st_as_sf(aus_stations, coords = c("longitude", "latitude"), crs = 4326)

# Perform the nearest neighbor join
nearest_stations <- st_nearest_feature(taipan_sf, aus_stations_sf)

# Combine the datasets
combined_data <- cbind(taipan_wild, aus_stations[nearest_stations, ])

combined_data <- as.data.frame(combined_data)
unique_id <- unique(combined_data$id)

Once we have successfully mapped the sighting data with each of the weather stations, let us try to observe the most frequent sightings with respect to its closest weather station.

Figure 2: Number of sightings for each weather station

Figure 2 illustrates the number of Coastal Taipan sightings for each of the weather stations in Australia. Based on the illustration, we will be able to narrow down our search for the location with frequent sightings of the reptile and can drill down our analysis to obtain weather information.

Here, we observe that the weather stations Cooktown Airport and Townsville Aero have significantly higher number of sightings when compared to the rest of the data.

the weather data obtained is for all the possible dates which match our time period filter. This does not necessarily mean that a Coastal Taipan was observed on that particular day. Hence, upon merging the weather and the sighting dataset, it is important to distinguish the days (obtained by eventDate) which mark the sighting of a Coastal Taipan. We will be primarily interested to analyse the prevailing weather conditions on these particular days for the choice of our weather stations.

4 Exploratory data analysis

4.1 When are the Coastal Taipans most likely to be observed ?

Figure 3: Monthly number of Coastal Taipan sightings in Australia

💡 Figure 3 illustrates the number of Coastal Taipans reported till date for each month. We can observe that the sightings are higher between the months of July to December when compared to the rest of the year. This can be a result of the prevailing monsoon conditions in Australia which closely corroborates with our assumption stated in Section 1.

Some of the reasons why the Coastal Taipans are observed to be more active are as follows:

1. Breeding season: The Coastal Taipans are highly active during the breeding season which closely conincides with the monsoon season in Australia.
2. Increased prey availability: The monsoon season in northern Australia typically brings heavy rainfall, which can lead to flooding in some areas. This flooding forces small mammals, reptiles, and other prey animals out of their burrows and hiding places, making them more accessible to Coastal Taipans. The increased prey availability during the monsoon can lead to an uptick in snake activity as they take advantage of the abundance of food.
3. Temperature and humidity: Reptiles are ectothermic in nature, meaning their body temperature is highly influenced by the environmental temperature. Monsoon season generally brings about warm and humid conditions. These conditions additionally improve the metabolism and mobility in reptiles which allows for higher activity and increased number of Coastal Taipan sightings.
4. Migratory behaviour: Due to increased mobility in the reptiles during the monsoon season, some Coastal Taipans exhibit migrate behaviour for better conditions and availability of prey. Migrations can often lead to human interactions and hence, their consequent sightings.

💡

4.2 Where are the Coastal Taipans most commonly observed in Australia?

Figure 4: Regions of Coastal Taipan sightings in Australia

Figure 4 illustrates that, in alignment with its name, most Coastal Taipan sightings occur in coastal regions.

💡💡 The Coastal Taipan’s preference for coastal regions in Australia can be attributed to the habitat, climate, and prey availability in these areas. Coastal regions provide a favorable environment with adequate warmth, humidity, and shelter. These conditions are conducive for the Taipan’s survival and reproduction. Additionally, coastal areas offer a rich biodiversity, ensuring ample prey for the snake. The vegetation in these regions, like grasslands and woodlands, offers suitable hiding spots for the snake and its prey, leading to a higher likelihood of the Taipan being found in these areas.

4.3 Has the geographical distribution of Coastal Taipans remained consistent over the years?

Snakes are typically reclusive and territorial. Given this characteristic, it’s intriguing to consider whether coastal taipans exhibit similar behavior. Specifically, it’s of interest to determine if coastal taipans remain in their established habitats due to their inherent nature or external factors or if there are distinct regions they consistently inhabit. This investigation will be facilitated by generating a null plot and conducting hypothesis testing. The pertinent hypotheses and the mechanism for generating the null distribution are outlined as follows:

\(H_o\): The geographical distribution of Coastal Taipan sightings has remained consistent over the years, with no significant difference in distribution between the periods pre-2000s and post-2000s.
\(H_1\): The geographical distribution of Coastal Taipan sightings has changed between the periods pre-2000s and post-2000s.

Null generating mechanism: Usage of the “null_permute” function to permute the eventCategory (Pre or Post 2000s categorisation) values of the Coastal Taipan sightings.

Figure 5: Null Distribution of Taipan Sightings by Location

Key takeaway

Upon analysing the plot null lineup plots in Figure 5, we observed that of the 8 test cases, only 2 people were able to recognise the plot 19 as the most unique plot due to the scatter points being limited to only the coastal regions of Australia. The P-value for the following result is 0.0572447 which suggests that the null hypothesis cannot be rejected based on 95% confidence and we can conclude that there is significant evidence in the data to suggest that Coastal Taipans are consistently sighted in the same regions in Australia over the years.

4.4 How are the weather conditions like in the areas with Coastal Taipan sightings ?

In this section, we will be interested to find any insights with respect to the weather in the locations with high Coastal Taipan sightings.

4.4.1 Does rain play a role in the sightings of the Coastal Taipans ? ⛈️

Figure 6: Number of Coastal Taipan sightings on days of observed precipitation

Key takeaway

Based on our analysis of Figure 6, we can observe that of the 27 observations, 23 of the sightings took place on days with no recorded precipitation while only 4 sightings took place on days with recorded precipitation. This suggests that the precipitation may not have a strong association with the Coastal Taipan sightings. However, it must also be kept in mind that the current sample of the dataset is too small to generate any strong conclusions from the data and we may require further data to support our analysis.

4.4.2 How are the temperatures during the days of sightings ? ☀️

Let us now explore the minimum and maximum temperatures on the given day of Coastal Taipan sightings and analyse any further insights.

Figure 7: Temperature range on the days of Coastal Taipan sightings

Key takeaway

Upon analysing the maximum and minimum temperatures on the days of Coastal Taipan sightings as illustrated by Figure 7, we can observe that the majority of the sightings were recorded on days with relatively higher maximum and minimum temperatures. This suggests that the mobility of the reptiles are higher during warmer conditions leading to higher probability of their sightings. Higher temperatures also induce lower mobility among the prey of the Taipans to protect themselves from the heat, as a result of which, the reptiles are also on the move to hunt.

The average maximum and minimum temperatures visualised by the two vertical lines in the plot are 28.1 and 19 degree celsius respectively, suggesting warm conditions.

5 PART 2 - Ecotourism & Tourism

5.1 Data description

load("data/tourism.rda")

tourism_subset <- tourism[tourism$Region %in% c("Ingham", "Townsville City - North Ward", "Mackay", "Tewantin","Rockhampton City", "Gladstone", "Redcliffe", "Cairns City", "Daintree"),]

The 9 tourism regions in the code chunk above were selected as they were available and overlapped in the most frequent sightings closest to weather stations as established in Figure 2. Moreover, ‘Daintree’ has been used as a proxy of ‘Cooktown’ due to the lack of data availability in the tourism data.

5.2 Task 1 - Tourism data

top_location <- c("Ingham", "Townsville City - North Ward", "Mackay", "Tewantin","Rockhampton City", "Gladstone", "Redcliffe", "Cairns City", "Daintree")

top_tourism <- tourism %>% filter(Region %in% top_location)

top_tourism <- top_tourism %>% 
  index_by(Quarter) %>% 
  group_by(Purpose) %>% 
  summarise(Trips = mean(Trips))

In the code chunk above, we subset the tourism dataset to the 9 chosen tourism regions only and calculate the total of the average trips for the 9 regions based on different travelling purpose.

Figure 8: Quarterly average tourism trips in selected regions, categorised by purpose

Figure 9: Total quarterly average tourism trips in selected regions

Note

• The interactive capabilities of Plotly have made it possible to discover that the majority of peaks corresponding to the various reasons for these trips occur in Quarter 3, upon analyzing the facet plot representing trip purposes.
• Based on those peaks, it is safe to assert that seasonality can be easily identified.
• We can also see an upward trend in the yearly trend for the number of trips taken to regions of Ingham, “Townsville City - North Ward, Mackay, Tewantin, Rockhampton City, Gladstone, Redcliffe, Cairns City, Daintree , with the exception of the sharp decline in 2020, which is primarily affected by the COVID-19 pandemic.

6 ECOTOURISM

top <- c("ingham composite", "townsville aero", "mackay aero", "tewantin rsl park", "rockhampton aero", "gladstone airport", "redcliffe", "cairns aero", "cooktown airport")

top_tourism_avg <- tourism %>% 
  filter(Region %in% top_location) %>% 
  filter(Purpose == "Total") %>%
  ungroup(Quarter) %>% 
  as_tibble() %>% 
  group_by(Region) %>% 
  summarise(Avg_trips = mean(Trips))

top_tourism_avg$Region[top_tourism_avg$Region == "Townsville City - North Ward"] <- "Townsville"

Quarterly average of total tourism trips for each of the selected regions was determined and made into a tibble.

What is Ecotourism?

Ecotourism encompasses nature-based activities and responsible travel that conserves the environment and increases visitor appreciation and understanding of natural and cultural values.

Why is Ecotourism important for the coastal Taipan? 🐍

For Queensland, where our regions are for which we subset our data - Tourism is a $23 billion industry. For the Coastal Taipan, the ecotourism industry allows visitors the chance to observe and appreciate this species in its natural habitat - without causing harm. Exploring and understanding sustainable ecotourism can be significant in ensuring its survival and protection for future generations.

7 Does the Data Suggest Ecotourist Interest in the Coastal Taipan?

7.1 Visual Inference of Ecotourism

As aforementioned, Queensland generates a lot of money from its tourism industry. Given this, it would be interesting to investigate the possibility of ecotourism centered around the coastal Taipan. To explore this, a null plot will be generated to investigate the relationship between tourist regions and coastal Taipan sightings.

\(H_o\) (null hypothesis): There is no association between popularity of the tourist regions and coastal Taipan sightings.

\(H_1\) (alternative hypothesis): There is an association between popular tourist regions and coastal Taipan sightings.

Null generating mechanism: usage of ‘null_permute’ function to permute the “Avg_trips” (quarterly average trips computing for the subset regions) values, breaking existing relationships between quarterly average trips and popular tourism regions.

Figure 10: Null Plot of Tourism and Taipan Sightings

# A tibble: 1 × 1
  .gaps
  <lgl>
1 TRUE 

# A tibble: 1 × 2
  Correlation `R-squared`
        <dbl>       <dbl>
1      0.0765     0.00585

Key takeaway

When analysing the null plots in Figure 10, we were able to deduce that 0 out of the 8 people asked were able to recognise plot 20 as the most unique plot, and this was based on not being able to see a pattern which stood out differently to the other plots. The p-value for the following result is 1. With an significance level of 0.05 set, the p-value derived suggests there is weak evidence against the null hypothesis (\(H_o\)) that is that there is no association between Taipan sightings and the popularity of tourist regions. Furthermore, we run a correlation test and linear regression model with wild sighting being the dependent variable and quarter average trips being the independent variable. The correlation (0.0765) between the two variables is insignificant as well as the R-square (0.0059) of the linear regression model is negligible.

Thus, with this p-value you would fail to reject the null hypothesis, as the data suggests there is no strong evidence of an association between the popular tourist regions and Taipan sightings.

pvisual(0,8,20)

     x simulated binom
[1,] 0         1     1

7.2 Does the data support ecotourism for the coastal Taipan?

To explore whether ecotourist interest may potentially exist for the Coastal Taipan, a map of Queensland was created using electoral division data retrieved from the Australian Electoral Commission. Layered on top of this map, we placed points representing the sightings of the Coastal Taipan. We also layered points which were illustrated major tourism regions, with size indicating popularity of that region. These points were collected using the RJSONIO library, which fetched latitude and longitude details for each selected tourist region in unique_regions_tourism utilising the OpenStreetMap’s Nominatim service.

The generated plot in Figure 11 showcases the regions in Queensland with Coastal Taipan sightings in blue and tourism regions in red. This plot therefore can assist in visualising the distribution of these points and proximity of tourism regions to Taipain sighting to get a better understanding in potential ecotourist interest in the Coastal Taipan, as well as if popularity in tourism region contributes to higher likelihood of sightings.

Figure 11: Map of Tourism Regions and Sightings

Ecotourism and Taipan Sightings

Referring to Figure 11, we can draw some insights in relation to Tourism Regions and Coastal Taipan sightings in Queensland:

1. Coastal Taipans, represented by the blue points can be seen predominantly along the eastern coast of Queesland, with some sightings further inland.
2. There’s overlap between Taipan sightings (blue points) and tourism regions (red points). This is evident towards the cost in southern and central parts of the state.
3. There are sightings, particularly in the northern part of Queensland where multiple coastal Taipan sightings can be observed, without overlap in tourism regions.

While there is some overlap in the coastal Taipan sightings and Tourist regions, there are also some important things to consider:

• The overlap between tourist regions and Taipan sightings does not necessarily indicate ecotourism centered around the Coastal Taipan. Queensland is known to be a popular tourist attraction, renowned for its diverse tourist attractions. For example, while Cairns city has overlap with Taipain sightings, its primarily known for its proximity to the Great Barrier Reef.

• Our analysis was constrained by lack of available data. A lot of the regions for which coastal Taipan were sighted did not overlap in the available tourism data. This impedes a comprehensive understanding of potential ecotourism for the coastal Taipan.

8 Summary

Based on our detailed analysis of the Coastal Taipan sightings, following are our key takeaways:

💡💡
The analysis focused on the behavior and distribution of Coastal Taipans (Oxyuranus Scutellatus Scutellatus) in the coastal regions of Queensland. The findings suggest that Coastal Taipans are territorial creatures, primarily inhabiting Queensland’s coastal areas, with potential migration towards the Northern Territory in the future.

Despite being less frequent in sightings, Coastal Taipans are not considered endangered. They are elusive and tend to avoid human contact, making their sightings rare as they prefer to stay within their habitats.

Contrary to popular belief, the data does not strongly support the idea that Coastal Taipans are more commonly sighted on days with recorded precipitation. However, they do exhibit higher mobility during the monsoon period, leading to an increase in sightings.

The research with the tourism dataset, initially focusing on regions near Townsville due to their connection to Coastal Taipan sightings. The study then narrowed its focus to Townsville City - North Ward, which had a significantly higher number of wild sightings compared to areas near the Townsville airport. Subsequently, the analysis identified the top nine regions with the highest number of wild sightings for temporal analysis: Ingham, Townsville City - North Ward, Mackay, Tewantin, Rockhampton City, Gladstone, Redcliffe, Cairns City, and Daintree.

The research merged the tourism dataset with the wild sighting data to investigate the relationship between tourism activity and the occurrences of Coastal Taipan sightings. The visualizations and more precise analysis, including permutation tests, were carried out. However, when eight individuals assessed these visuals, none of them could identify distinctions among the representations, which seemed to be due to chance rather than any valid reasons.

The hypothesis testing led to a p-value of 1, resulting in a failure to reject the null hypothesis (\(H_o\)): There is no association between the popularity of tourist regions and Coastal Taipan sightings.

In summary, the study reveals that Coastal Taipans are territorial and not endangered, although they are reclusive and rarely seen due to their preference for isolated habitats. The data does not strongly support the idea that precipitation directly influences their sightings. and the analysis of tourism data did not find a significant association between tourist popularity and Coastal Taipan sightings, as indicated by the p-value of 1.

💡💡

9 Citations:

1. Atlas of Living Australia (ALA) - Belbin L, Wallis E, Hobern D, Zerger A (2021) The Atlas of Living Australia: History, current state and future directions. Biodiversity Data Journal 9: e65023. https://doi.org/10.3897/BDJ.9.e65023

2. The galah package - Westgate M, Kellie D, Stevenson M, Newman P (2023). galah: Biodiversity Data from the Living Atlas Community. R package version 1.5.3, https://CRAN.R-project.org/package=galah.

3. Tidyverse - Wickham H, Averick M, Bryan J, Chang W, McGowan LD, François R, Grolemund G, Hayes A, Henry L, Hester J, Kuhn M, Pedersen TL, Miller E, Bache SM, Müller K, Ooms J, Robinson D, Seidel DP, Spinu V, Takahashi K, Vaughan D, Wilke C, Woo K, Yutani H (2019). “Welcome to the tidyverse.” Journal of Open Source Software, 4(43), 1686. doi:10.21105/joss.01686 https://doi.org/10.21105/joss.01686.

4. ggplot2 - H. Wickham. ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York, 2016.

5. rnoaa - Chamberlain S, Hocking D (2023). rnoaa: ‘NOAA’ Weather Data from R. R package version 1.4.0, https://CRAN.R-project.org/package=rnoaa.

6. broom - Robinson D, Hayes A, Couch S (2023). broom: Convert Statistical Objects into Tidy Tibbles. R package version 1.0.5, https://CRAN.R-project.org/package=broom.

7. leaflet - Cheng J, Schloerke B, Karambelkar B, Xie Y (2023). leaflet: Create Interactive Web Maps with the JavaScript ‘Leaflet’ Library. R package version 2.2.0, https://CRAN.R-project.org/package=leaflet.

8. ggalt - Rudis B, Bolker B, Schulz J (2017). ggalt: Extra Coordinate Systems, ‘Geoms’, Statistical Transformations, Scales and Fonts for ‘ggplot2’. R package version 0.4.0, https://CRAN.R-project.org/package=ggalt.

9. ggpubr - Kassambara A (2023). ggpubr: ‘ggplot2’ Based Publication Ready Plots. R package version 0.6.0, https://CRAN.R-project.org/package=ggpubr.

10. kableExtra - Zhu H (2021). kableExtra: Construct Complex Table with ‘kable’ and Pipe Syntax. R package version 1.3.4, https://CRAN.R-project.org/package=kableExtra.

11. nullabor -Buja, A., Cook, D., Hofmann, H., Lawrence, M., Lee, E.-K., Swayne, D. F, Wickham, H. (2009) Statistical Inference for Exploratory Data Analysis and Model Diagnostics Royal Society Philosophical Transactions A, 367(1906):4361-4383. URL http://rsta.royalsocietypublishing.org/content/367/1906/4361.article-info

12. ggmap - D. Kahle and H. Wickham. ggmap: Spatial Visualization with ggplot2. The R Journal, 5(1), 144-161. URL http://journal.r-project.org/archive/2013-1/kahle-wickham.pdf

13. maps - Becker OScbRA, Minka ARWRvbRBEbTP, Deckmyn. A (2022). maps: Draw Geographical Maps. R package version 3.4.1, https://CRAN.R-project.org/package=maps.

14. ggthemes -Arnold J (2021). ggthemes: Extra Themes, Scales and Geoms for ‘ggplot2’. R package version 4.2.4, https://CRAN.R-project.org/package=ggthemes.

15. sf - Pebesma, E., & Bivand, R. (2023). Spatial Data Science: With Applications in R. Chapman and Hall/CRC. https://doi.org/10.1201/9780429459016

16. R Studio - Integrated Development for R. RStudio, PBC, Boston, MA URL http://www.rstudio.com/.

17. plotly - C. Sievert. Interactive Web-Based Data Visualization with R, plotly, and shiny. Chapman and Hall/CRC Florida, 2020.